Computer Science - Programming Languages
Subcategories
Papers
LLM4Decompile: Decompiling Binary Code with Large Language Models
Hanzhuo Tan, et al. • (2024) • DOI:
10.48550/arXiv.2403.05286
Decompilation aims to convert binary code to high-level source code, but traditional tools like Ghidra often produce results that are difficult to read and execute. Motivated by the advancements in La...
Transformers are Efficient Compilers, Provably
Xiyu Zhai, et al. • (2025) • DOI:
10.48550/arXiv.2410.14706
Transformer-based large language models (LLMs) have demonstrated surprisingly robust performance across a wide range of language-related tasks, including programming language understanding and generat...
Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs
Alexander K. Lew, et al. •
• (2023) • DOI:
10.48550/arXiv.2306.03081
Even after fine-tuning and reinforcement learning, large language models (LLMs) can be difficult, if not impossible, to control reliably with prompts alone. We propose a new inference-time approach to...